Independent and automatic evaluation of acoustic-to-articulatory inversion models
This work addresses the need for robust, speaker-independent articulatory reconstruction to improve speech recognition and synthesis, though it is incremental as it focuses on evaluation rather than a new model.
The paper tackled the problem of evaluating acoustic-to-articulatory inversion models for speaker independence and dataset merging, introducing a new evaluation method based on the phone discrimination ABX task and applying it to a Bi-LSTM model trained on 14 speakers across 3 datasets.
Reconstruction of articulatory trajectories from the acoustic speech signal has been proposed for improving speech recognition and text-to-speech synthesis. However, to be useful in these settings, articulatory reconstruction must be speaker independent. Furthermore, as most research focuses on single, small datasets with few speakers, robust articulatory reconstrucion could profit from combining datasets. Standard evaluation measures such as root mean square error and Pearson correlation are inappropriate for evaluating the speaker-independence of models or the usefulness of combining datasets. We present a new evaluation for articulatory reconstruction which is independent of the articulatory data set used for training: the phone discrimination ABX task. We use the ABX measure to evaluate a Bi-LSTM based model trained on 3 datasets (14 speakers), and show that it gives information complementary to the standard measures, and enables us to evaluate the effects of dataset merging, as well as the speaker independence of the model.